© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110571
    Prev
    Next
    INDEX
    Explanations

    script dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /res
    -0.08
    localized
    -0.08
     polynomial
    -0.08
     ක්
    -0.08
    estial
    -0.08
     العمليات
    -0.08
    ερ
    -0.08
     vực
    -0.08
     ‎
    -0.08
     הכל
    -0.07
    POSITIVE LOGITS
     persu
    0.10
    采访
    0.10
     conversaciones
    0.09
     चर्चा
    0.09
    参加
    0.09
    记者
    0.08
     erneut
    0.08
     goodbye
    0.08
    ताना
    0.08
    会议
    0.08
    Activations Density 0.066%

    No Known Activations